Continual Person Identification using Footstep-Induced Floor Vibrations on Heterogeneous Floor Structures
This work addresses the need for privacy-friendly, non-intrusive person identification in buildings without requiring pre-collected data or direct line-of-sight, though it is incremental as it builds on prior vibration sensing methods.
The paper tackled the problem of continual person identification in smart buildings by addressing the high variability in footstep-induced floor vibration data due to structural heterogeneity and human gait variations, achieving a 70% variability reduction and 90% accuracy in online identification with 20 people.
Person identification is important for smart buildings to provide personalized services such as health monitoring, activity tracking, and personnel management. However, previous person identification relies on pre-collected data from everyone, which is impractical in many buildings and public facilities in which visitors are typically expected. This calls for a continual person identification system that gradually learns people's identities on the fly. Existing studies use cameras to achieve this goal, but they require direct line-of-sight and also have raised privacy concerns in public. Other modalities such as wearables and pressure mats are limited by the requirement of device-carrying or dense deployment. Thus, prior studies introduced footstep-induced structural vibration sensing, which is non-intrusive and perceived as more privacy-friendly. However, this approach has a significant challenge: the high variability of vibration data due to structural heterogeneity and human gait variations, which makes online person identification algorithms perform poorly. In this paper, we characterize the variability in footstep-induced structural vibration data for accurate online person identification. To achieve this, we quantify and decompose different sources of variability and then design a feature transformation function to reduce the variability within each person's data to make different people's data more separable. We evaluate our approach through field experiments with 20 people. The results show a 70% variability reduction and a 90% accuracy for online person identification.